{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gnndld-graph-neural-network-with-directional","title":"GNNDLD: Graph Neural Network with Directional Label Distribution","arxiv_id":null,"date":"2024-02-26","proceeding":"International Conference on Agents and Artificial Intelligence, ICAART 2024 2","authors":["Chandramani Chaudhary","Nirmal Kumar Boran","N Sangeeth","and Virendra Singh"],"abstract":"By leveraging graph structure, Graph Neural Networks (GNN) have emerged as a useful model for graph-based\r\ndatasets. While it is widely assumed that GNNs outperform basic neural networks, recent research shows that\r\nfor some datasets, neural networks outperform GNNs. Heterophily is one of the primary causes of GNN\r\nperformance degradation, and many models have been proposed to handle it. Furthermore, some intrinsic\r\ninformation in graph structure is often overlooked, such as edge direction. In this work, we propose GNNDLD,\r\na model which exploits the edge direction and label distribution around a node in varying neighborhoods\r\n(hop-wise). We combine features from all layers to retain both low-pass frequency and high-pass frequency\r\ncomponents of a node because different layers of neural networks provide different types of information. In\r\naddition, to avoid oversmoothing, we decouple the node feature aggregation and transformation operations.\r\nBy combining all of these concepts, we present a simple yet very efficient model. Experiments on six standard\r\nreal-world datasets show the superiority of GNNDLD over the state-of-the-art models in both homophily and\r\nheterophily.","url_abs":"https://www.scitepress.org/Papers/2024/123214/","url_pdf":"https://www.scitepress.org/Papers/2024/123214/123214.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-chameleon-60-20-20","task":"Node Classification","dataset":"Chameleon (60%/20%/20% random splits)","model":"GNNDLD","rank_in_archive_order":1,"of":38,"metrics":{"1:1 Accuracy":"79.78±1.66"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-citeseer-60-20-20","task":"Node Classification","dataset":"CiteSeer (60%/20%/20% random splits)","model":"GNNDLD","rank_in_archive_order":1,"of":33,"metrics":{"1:1 Accuracy":"86.3±1.24"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-60-20-20-random","task":"Node Classification","dataset":"Cora (60%/20%/20% random splits)","model":"GNNDLD","rank_in_archive_order":1,"of":33,"metrics":{"1:1 Accuracy":"92.99 ±0.9"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-film-60-20-20-random","task":"Node Classification","dataset":"Film (60%/20%/20% random splits)","model":"GNNDLD","rank_in_archive_order":1,"of":37,"metrics":{"1:1 Accuracy":"75.69±0.78"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed-60-20-20-random","task":"Node Classification","dataset":"PubMed (60%/20%/20% random splits)","model":"GNNDLD","rank_in_archive_order":1,"of":37,"metrics":{"1:1 Accuracy":"91.95±0.19 "},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel-60-20-20","task":"Node Classification","dataset":"Squirrel (60%/20%/20% random splits)","model":"GNNDLD","rank_in_archive_order":1,"of":37,"metrics":{"1:1 Accuracy":"77.72±0.84 "},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}